A charging environment temperature monitoring and alarm system based on artificial intelligence

By introducing a heat monitoring module and an abnormality check module in the charging ambient temperature monitoring and alarm system, combined with artificial intelligence technology, dynamically monitor and predict the heating status of the charging piles, the problem that existing systems cannot accurately monitor and improve the safety of the charging piles and processing efficiency.

CN118258516BActive Publication Date: 2024-11-01GUANGDONG HAOYIDIAN TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410425250.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-04-10
Publication Date
2024-11-01
Estimated Expiration
2044-04-10

AI Technical Summary

Technical Problem

The existing charging environment temperature monitoring and alarm system cannot dynamically monitor the heating status of the charging pile in combination with the charging pile application environment, resulting in inaccurate temperature monitoring results and low efficiency.

Method used

Design a charging environment temperature monitoring and alarm system based on artificial intelligence, including a heating monitoring module, anomaly detection module and an operation prediction module. By obtaining the temperature parameters and current values ​​of the charging pile in real time, calculating the heating coefficient and environmental coefficient, dynamic monitoring and prediction The heating state of the charging pile and judge the cause of the abnormality based on the abnormal signal to improve the processing efficiency.

Benefits of technology

Real-time monitoring of the heating status of the charging pile and rapid identification of abnormal causes, improve the safety of the charging pile and the efficiency of abnormal handling, and avoid the occurrence of charging accidents.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118258516B_ABST
    Figure CN118258516B_ABST
Patent Text Reader

Abstract

The present invention belongs to the field of charging monitoring and relates to data analysis technology. It is used to solve the problem that the existing charging environment temperature monitoring and alarm system cannot dynamically monitor the heating state of the charging pile in combination with the application environment of the charging pile. Specifically, it is a charging environment temperature monitoring and alarm system based on artificial intelligence, including a heating monitoring module, an abnormality investigation module, an operation prediction module, a controller and a storage module; the heating monitoring module is communicatively connected with the abnormality investigation module and the operation monitoring module, the storage module is communicatively connected with the heating monitoring module, the abnormality investigation module and the operation prediction module, and the abnormality investigation module is also communicatively connected with the controller; the present invention can perform heating monitoring and analysis on the charging pile, obtain the heating coefficient by comprehensively analyzing and calculating various temperature parameters of the charging pile, and issue an early warning at the first time when heating abnormality occurs to avoid more serious charging accidents.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of charging monitoring and relates to data analysis technology, and specifically is a charging environment temperature monitoring and alarm system based on artificial intelligence. Background Art

[0002] A charging pile refers to a charging device that provides energy for electric vehicles. Its function is similar to that of a gas pump in a gas station. It can be fixed on the ground or on a wall and installed in parking lots or charging stations in public buildings and residential areas. It can charge various models of electric vehicles according to different voltage levels.

[0003] The existing charging environment temperature monitoring and alarm system lacks the function of troubleshooting the abnormal causes when the temperature is abnormal. After receiving the abnormal signal, the management personnel need to spend a lot of time to detect the abnormal factors before they can handle the abnormality, resulting in low efficiency of abnormal handling; at the same time, the existing charging environment temperature monitoring and alarm system can only perform temperature monitoring and early warning according to a fixed threshold, and cannot dynamically monitor the heating state of the charging pile in combination with the application environment of the charging pile, resulting in the problem of low accuracy of the charging pile temperature monitoring results.

[0004] In view of the above technical problems, the present invention proposes a solution. Summary of the invention

[0005] The purpose of the present invention is to provide a charging environment temperature monitoring and alarm system based on artificial intelligence, which is used to solve the problem that the existing charging environment temperature monitoring and alarm system cannot dynamically monitor the heating state of the charging pile in combination with the application environment of the charging pile;

[0006] The technical problem to be solved by the present invention is: how to provide an artificial intelligence-based charging environment temperature monitoring and alarm system that can dynamically monitor the heating state of the charging pile in combination with the application environment of the charging pile.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] A charging environment temperature monitoring and alarm system based on artificial intelligence, comprising a fever monitoring module, an abnormality troubleshooting module, an operation prediction module, a controller and a storage module; the fever monitoring module is communicatively connected with the abnormality troubleshooting module and the operation monitoring module, the storage module is communicatively connected with the fever monitoring module, the abnormality troubleshooting module and the operation prediction module, and the abnormality troubleshooting module is also communicatively connected with the controller;

[0009] The heating monitoring module is used to perform heating monitoring and analysis on the charging pile: marking the charging pile as a monitoring object, obtaining the heating coefficient FR of the monitoring object in real time, and judging whether the heating state of the monitoring object meets the requirements according to the value of the heating coefficient FR;

[0010] The abnormality troubleshooting module is used to mark the cause of abnormal heating of the charging pile and obtain the discharge value and the wave current value, and generate an environmental adjustment signal, a contact abnormality signal, a short circuit signal or a matching abnormality signal according to the numerical values ​​of the discharge value and the wave current value;

[0011] The operation prediction module is used to predict and analyze the operation status of the charging pile: generate a prediction cycle, divide the prediction cycle into several prediction time periods, obtain the ambient humidity data HS, ambient temperature data HW and altitude data HB of the monitored object at the beginning of the prediction cycle, and perform numerical calculations to obtain the environmental coefficient HJ of the monitored object; and predict whether the monitored object will have abnormal heating during the prediction cycle based on the environmental coefficient HJ.

[0012] As a preferred embodiment of the present invention, the process of obtaining the heating coefficient FR of the monitored object includes: obtaining box temperature data XW, air temperature data KW and temperature conduction data DW; the box temperature data XW of the monitored object is the inner wall temperature value of the chassis of the monitored object, the air temperature data KW of the monitored object is the air temperature value inside the monitored object, and the temperature conduction data DW of the monitored object is the outer surface temperature value of the wire connected to the output end of the monitored object; the heating coefficient FR of the monitored object is obtained by numerically calculating the box temperature data XW, the air temperature data KW and the temperature conduction data DW.

[0013] As a preferred embodiment of the present invention, the specific process of determining whether the fever state of the monitored object meets the requirements includes: obtaining the fever threshold FRmax through the storage module, and comparing the fever coefficient FR of the monitored object with the fever threshold FRmax: if the fever coefficient FR is less than the fever threshold FRmax, it is determined that the fever state of the monitored object meets the requirements; if the fever coefficient FR is greater than or equal to the fever threshold FRmax, it is determined that the fever state of the monitored object does not meet the requirements, and the fever monitoring module sends a fever abnormality signal to the abnormality detection module.

[0014] As a preferred embodiment of the present invention, the process of obtaining the discharge value and the wave current value includes: marking L1 seconds after the time when the abnormal heating signal is received as the troubleshooting period, dividing the troubleshooting period into several sub-periods, obtaining the maximum current value of the output circuit of the monitored object in the sub-period and marking it as the meter value of the sub-period, summing and averaging the meter values ​​of the monitored object in all sub-periods to obtain the discharge value of the monitored object, and performing variance calculation on the meter values ​​of the monitored object in all sub-periods to obtain the wave current value of the monitored object.

[0015] As a preferred embodiment of the present invention, the specific process of marking the cause of abnormal heating of the monitored object includes: obtaining the drainage threshold and the wave flow threshold through the storage module, and numerically comparing the drainage value and the wave flow value with the drainage value and the wave flow value respectively: if the drainage value is less than or equal to the drainage threshold and the wave flow value is less than or equal to the wave flow threshold, it is determined that the cause of the abnormal heating is an abnormal external environment, and the abnormality investigation module sends an environmental adjustment signal to the mobile phone terminal of the administrator; if the drainage value is less than or equal to the drainage threshold and the wave flow value is greater than the wave flow threshold, it is determined that the cause of the abnormal heating is poor contact of the wire, and the abnormality investigation module sends a contact abnormality signal to the mobile phone terminal of the administrator; if the drainage value is greater than the drainage threshold and the wave flow value is less than or equal to the wave flow threshold, it is determined that the cause of the abnormal heating is a line short circuit, and the abnormality investigation module sends a short circuit signal to the controller and the mobile phone terminal of the administrator, and the controller cuts off the output line of the monitored object after receiving the short circuit signal; if the drainage value is greater than the drainage threshold and the wave flow value is greater than the wave flow threshold, it is determined that the cause of the abnormal heating is a mismatch between the wire and the equipment, and the abnormality investigation module sends a matching abnormality signal to the mobile phone terminal of the administrator.

[0016] As a preferred embodiment of the present invention, the process of obtaining the ambient humidity data HS includes: obtaining the air humidity value and humidity range of the external environment of the monitored object, marking the average value of the maximum value and the minimum value of the humidity range as the humidity mean value, and marking the absolute value of the difference between the air humidity value and the humidity mean value as the ambient humidity data HS; the process of obtaining the ambient temperature data HW includes: obtaining the air temperature value and temperature range of the external environment of the monitored object, marking the absolute value of the difference between the maximum value and the minimum value of the temperature range as the temperature mean value, and marking the absolute value of the difference between the air temperature value and the temperature mean value as the ambient temperature data HW; the altitude data HB is the altitude value of the monitored object.

[0017] As a preferred embodiment of the present invention, the specific process of predicting whether the monitored object has abnormal heating within the prediction period includes: obtaining an environmental interval matching the environmental coefficient HJ of the monitored object through a storage module and marking it as a marked interval, marking the heating data of the charging pile within the marked interval within the corresponding prediction period as marked data; establishing a rectangular coordinate system with the prediction period time as the X-axis and the heating coefficient FR of the monitored object within the prediction period as the Y-axis, marking a number of monitoring points in the rectangular coordinate system with the start time of the prediction period as the horizontal coordinate and the maximum value of the heating coefficient FR of the monitored object within the prediction period as the vertical coordinate, and connecting the monitoring points from left to right in sequence to obtain a monitoring polyline; and connecting the marked data with the corresponding prediction period. During the period, several marked broken lines are marked in the rectangular coordinate system, and the horizontal coordinate value of the monitoring point on the far right of the monitoring broken line is marked as Lo. A ray perpendicular to the X-axis is made in the first quadrant of the rectangular coordinate system with the prediction point as the endpoint and marked as the prediction ray. The coordinates of the prediction point are (Lo, 0). The monitoring broken line, the marked broken line, the Y-axis and the prediction ray constitute multiple closed polygons. The sum of the area values ​​of all closed polygons is marked as the fitting value of the marked broken line. The marked broken line with the smallest fitting value is marked as the matching broken line. It is determined whether the charging pile corresponding to the matching broken line has abnormal heating in the corresponding prediction period: if so, a prediction warning signal is generated and sent to the mobile terminal of the manager; if not, no signal is generated.

[0018] As a preferred embodiment of the present invention, after the prediction cycle is completed, the environmental coefficient HJ and the heating coefficient FR of the monitored object are sent to the storage module for storage. After receiving the environmental coefficient HJ of the monitored object, the storage module updates the environmental interval: the environmental range is composed of the maximum value of the environmental coefficient HJ and the environmental coefficient HJmin, the environmental range is divided into several environmental intervals, and the heating coefficient FR of the monitored object is matched with the corresponding environmental interval.

[0019] The present invention has the following beneficial effects:

[0020] 1. The heating monitoring module can be used to monitor and analyze the heating of the charging pile. The heating coefficient can be obtained by comprehensive analysis and calculation of various temperature parameters of the charging pile. Then, the heating state of the monitored object can be monitored in real time through the heating coefficient. In the event of abnormal heating, an early warning can be issued at the first time to avoid more serious charging accidents and improve the safety of the charging pile.

[0021] 2. The abnormality troubleshooting module can be used to troubleshoot and analyze the causes of abnormal heating of the charging pile. The discharge value and wave current value are obtained by analyzing the current value when the charging pile has abnormal heating. The causes of abnormal heating are checked and matched according to the current change law when the charging pile is abnormally heated due to different reasons. After the abnormal heating occurs, the abnormal cause can be directly output synchronously to improve the efficiency of abnormality handling.

[0022] 3. By running the prediction module, the operating status of the charging pile can be predicted and analyzed. Combined with the application environment of the charging pile, historical data of the environmental range that matches the environmental coefficient is selected for overlap analysis, so as to filter out the curve of the heating coefficient that is closest to the monitored object from the historical data, and then predict the heating anomaly of the monitored object according to the heating monitoring results of the marked broken line. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0024] Figure 1 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0025] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] Embodiment 1

[0027] like Figure 1 As shown, an artificial intelligence-based charging environment temperature monitoring and alarm system includes a fever monitoring module, an abnormality troubleshooting module, an operation prediction module, a controller and a storage module; the fever monitoring module is communicatively connected to the abnormality troubleshooting module and the operation monitoring module, the storage module is communicatively connected to the fever monitoring module, the abnormality troubleshooting module and the operation prediction module, and the abnormality troubleshooting module is also communicatively connected to the controller.

[0028] The heating monitoring module is used to perform heating monitoring and analysis on the charging pile: mark the charging pile as the monitoring object, and obtain the box temperature data XW, air temperature data KW and thermal conductivity data DW of the monitoring object in real time; the box temperature data XW of the monitoring object is the inner wall temperature value of the chassis of the monitoring object, the air temperature data KW of the monitoring object is the air temperature value inside the monitoring object, and the thermal conductivity data DW of the monitoring object is the outer surface temperature value of the wire connected to the output end of the monitoring object; the heating coefficient FR of the monitoring object is obtained by the formula FR=α1*DW+α2*KW+α3*XW. The heating coefficient FR is a value that reflects the degree of heating state of the monitoring object. The larger the value of the heating coefficient, the worse the heating state of the monitoring object is; wherein α1, α2 and α3 are all proportional coefficients, and α1>α2> α3>1; the heating threshold FRmax is obtained through the storage module, and the heating coefficient FR of the monitored object is compared with the heating threshold FRmax: if the heating coefficient FR is less than the heating threshold FRmax, it is determined that the heating state of the monitored object meets the requirements; if the heating coefficient FR is greater than or equal to the heating threshold FRmax, it is determined that the heating state of the monitored object does not meet the requirements, and the heating monitoring module sends a heating abnormality signal to the abnormality troubleshooting module; the charging pile is monitored and analyzed for heating, and the heating coefficient is obtained by comprehensive analysis and calculation of various temperature parameters of the charging pile, and then the heating state of the monitored object can be monitored in real time through the heating coefficient, and an early warning is issued as soon as a heating abnormality occurs, so as to avoid more serious charging accidents and improve the safety of the use of the charging pile.

[0029] The abnormality investigation module is used to investigate and analyze the cause of abnormal heating of the charging pile: L1 seconds after the time of receiving the abnormal heating signal is marked as the investigation period, L1 is a numerical constant, and the value of L1 is set by the management personnel; the investigation period is divided into several sub-periods, the maximum current value of the output circuit of the monitored object in the sub-period is obtained and marked as the meter value of the sub-period, the meter values ​​of the monitored object in all sub-periods are summed and averaged to obtain the discharge value of the monitored object, the meter values ​​of the monitored object in all sub-periods are calculated to obtain the wave flow value of the monitored object, the discharge threshold and the wave flow threshold are obtained through the storage module, and the discharge value and the wave flow value are numerically compared with the discharge value and the wave flow value respectively: if the discharge value is less than or equal to the discharge threshold and the wave flow value is less than or equal to the wave flow threshold, it is determined that the cause of the abnormal heating is an abnormal external environment, and the abnormality investigation module sends an environmental adjustment signal to the management personnel's mobile phone terminal; if the discharge value is less than or equal to the discharge threshold and the wave flow value is greater than the wave flow threshold, it is determined that the cause of the abnormal heating is poor contact of the wire, and the abnormality investigation module sends a contact abnormality signal to the mobile phone terminal of the administrator; if the discharge value is greater than the discharge threshold and the wave current value is less than or equal to the wave current threshold, it is determined that the cause of the abnormal heating is a line short circuit, and the abnormality investigation module sends a short circuit signal to the controller and the mobile phone terminal of the administrator, and the controller cuts off the output line of the monitored object after receiving the short circuit signal; if the discharge value is greater than the discharge threshold and the wave current value is greater than the wave current threshold, it is determined that the cause of the abnormal heating is mismatched wires and equipment, and the abnormality investigation module sends a matching abnormality signal to the mobile phone terminal of the administrator; the cause of the abnormal heating of the charging pile is investigated and analyzed, and the discharge value and the wave current value are obtained by performing data analysis on the current value when the charging pile has abnormal heating, so as to investigate and match the cause of the abnormal heating in combination with the current change law when the charging pile is subjected to different reasons for abnormal heating, so as to directly output the abnormal cause synchronously after the abnormal heating occurs, thereby improving the efficiency of abnormal handling.

[0030] The operation prediction module is used to predict and analyze the operation status of the charging pile: generate a prediction cycle, divide the prediction cycle into several prediction periods, and obtain the ambient humidity data HS, ambient temperature data HW and altitude data HB of the monitored object at the beginning of the prediction cycle. The process of obtaining the ambient humidity data HS includes: obtaining the air humidity value and humidity range of the external environment of the monitored object, marking the average value of the maximum and minimum values ​​of the humidity range as the wet mean value, and marking the absolute value of the difference between the air humidity value and the wet mean value as the ambient humidity data HS; the process of obtaining the ambient temperature data HW includes: obtaining the air temperature value and temperature range of the external environment of the monitored object, marking the absolute value of the difference between the maximum and minimum values ​​of the temperature range as the temperature mean value, and marking the absolute value of the difference between the air temperature value and the temperature mean value. The absolute value of the difference is marked as ambient temperature data HW; the altitude data HB is the altitude value of the monitored object; the environmental coefficient HJ of the monitored object is obtained through the formula HJ=β1*HS+β2*HW+β3*HB. The environmental coefficient is a value that reflects the quality of the operating environment of the monitored object. The larger the value of the environmental coefficient, the worse the operating environment of the monitored object; β1, β2 and β3 are all proportional coefficients, and β1>β2>β3>1; the environmental interval matching the environmental coefficient HJ of the monitored object is obtained through the storage module and marked as the marked interval, and the heating data of the charging pile in the marked interval in the corresponding prediction period is marked as the marked data; the prediction period time is taken as the X-axis and the monitoring object is taken as the prediction period. A rectangular coordinate system is established with the heating coefficient FR as the Y-axis, and a number of monitoring points are marked in the rectangular coordinate system with the start time of the prediction period as the horizontal coordinate and the maximum heating coefficient FR of the monitored object in the prediction period as the vertical coordinate. The monitoring points are connected from left to right in sequence to obtain a monitoring polyline; a number of marked polylines are marked in the rectangular coordinate system with the marked data and the corresponding prediction period, and the abscissa value of the monitoring point on the rightmost side of the monitoring polyline is marked as Lo. A ray perpendicular to the X-axis is made in the first quadrant of the rectangular coordinate system with the prediction point as the endpoint and marked as the prediction ray. The coordinates of the prediction point are (Lo, 0). The monitoring polyline, the marked polyline, the Y-axis and the prediction ray constitute multiple closed polygons. The area values ​​of all closed polygons are The sum value is marked as the fitting value of the marked polyline, and the marked polyline with the smallest fitting value is marked as the matching polyline. It is determined whether the charging pile corresponding to the matching polyline has abnormal heating in the corresponding prediction period: if so, a prediction warning signal is generated and sent to the mobile terminal of the manager; if not, no signal is generated; after the prediction period is completed, the environmental coefficient HJ and the heating coefficient FR of the monitored object are sent to the storage module for storage. After receiving the environmental coefficient HJ of the monitored object, the storage module updates the environmental interval: the maximum value of the environmental coefficient HJ and the environmental coefficient HJmin constitute the environmental range, the environmental range is divided into several environmental intervals, and the heating coefficient FR of the monitored object is matched with the corresponding environmental interval;Predict and analyze the operating status of the charging pile, combine the application environment of the charging pile, select the historical data of the environmental interval that matches the environmental coefficient for overlap analysis, and select the curve of the heating coefficient that is closest to the monitored object from the historical data, and then predict the heating anomaly of the monitored object according to the heating monitoring results of the marked broken line. ;

[0031] A charging environment temperature monitoring and alarm system based on artificial intelligence performs heating monitoring and analysis on charging piles when working: the charging piles are marked as monitoring objects, the box temperature data XW, the air temperature data KW and the temperature conduction data DW of the monitoring objects are obtained in real time, and the heating coefficient FR is numerically calculated to obtain the heating coefficient FR, and whether the heating state of the monitoring object is abnormal is judged by the heating coefficient FR; the causes of abnormal heating of the charging piles are investigated and analyzed: L1 seconds after the time when the abnormal heating signal is received is marked as the investigation period, the investigation period is divided into several sub-periods, the maximum current value of the output circuit of the monitoring object in the sub-period is obtained and marked as the meter value of the sub-period, the meter values ​​of the monitoring object in all sub-periods are summed and averaged to obtain the discharge value of the monitoring object, the variance of the meter values ​​of the monitoring object in all sub-periods is calculated to obtain the wave current value of the monitoring object, and the causes of abnormal heating of the monitoring object are judged by the numerical values ​​of the discharge value and the wave current value.

[0032] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

[0033] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula close to the real value. The coefficients in the formula are set by technicians in this field according to the actual situation; for example: formula FR=α1*DW+α2*KW+α3*XW; technicians in this field collect multiple groups of sample data and set the corresponding heating coefficient for each group of sample data; substitute the set heating coefficient and the collected sample data into the formula, any three formulas constitute a three-variable linear equation group, screen the calculated coefficients and take the average, and obtain the values ​​of α1, α2 and α3 as 6.48, 5.26 and 3.82 respectively;

[0034] The size of the coefficient is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the coefficient depends on the amount of sample data and the preliminary setting of the corresponding heating coefficient for each set of sample data by technical personnel in this field; as long as it does not affect the proportional relationship between the parameter and the quantified value, such as the heating coefficient is proportional to the value of the box temperature data.

[0035] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0036] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A charging environment temperature monitoring and alarm system based on artificial intelligence, characterized in that: It includes a fever monitoring module, an abnormality troubleshooting module, an operation prediction module, a controller and a storage module; the fever monitoring module is communicatively connected with the abnormality troubleshooting module and the operation monitoring module, the storage module is communicatively connected with the fever monitoring module, the abnormality troubleshooting module and the operation prediction module, and the abnormality troubleshooting module is also communicatively connected with the controller; The heating monitoring module is used to perform heating monitoring and analysis on the charging pile: marking the charging pile as a monitoring object, obtaining the heating coefficient FR of the monitoring object in real time, and judging whether the heating state of the monitoring object meets the requirements according to the value of the heating coefficient FR; The abnormality troubleshooting module is used to mark the cause of abnormal heating of the charging pile and obtain the discharge value and the wave current value, and generate an environmental adjustment signal, a contact abnormality signal, a short circuit signal or a matching abnormality signal according to the numerical values ​​of the discharge value and the wave current value; The operation prediction module is used to predict and analyze the operation status of the charging pile: generate a prediction cycle, divide the prediction cycle into several prediction periods, obtain the ambient humidity data HS, ambient temperature data HW and altitude data HB of the monitored object at the beginning of the prediction cycle, and perform numerical calculation to obtain the environmental coefficient HJ of the monitored object; The environmental coefficient HJ is used to predict whether the monitored object will have abnormal heating during the prediction period; The process of obtaining the heating coefficient FR of the monitored object includes: obtaining box temperature data XW, air temperature data KW and temperature conduction data DW; the box temperature data XW of the monitored object is the temperature value of the inner wall of the box of the monitored object, the air temperature data KW of the monitored object is the air temperature value inside the monitored object, and the temperature conduction data DW of the monitored object is the temperature value of the outer surface of the wire connected to the output end of the monitored object; the heating coefficient FR of the monitored object is obtained by numerically calculating the box temperature data XW, the air temperature data KW and the temperature conduction data DW; The specific process of determining whether the fever state of the monitored object meets the requirements includes: obtaining the fever threshold FRmax through the storage module, comparing the fever coefficient FR of the monitored object with the fever threshold FRmax: if the fever coefficient FR is less than the fever threshold FRmax, it is determined that the fever state of the monitored object meets the requirements; if the fever coefficient FR is greater than or equal to the fever threshold FRmax, it is determined that the fever state of the monitored object does not meet the requirements, and the fever monitoring module sends a fever abnormality signal to the abnormality troubleshooting module; The process of obtaining the discharge value and the wave current value includes: marking L1 seconds after the moment of receiving the abnormal heating signal as the troubleshooting period, dividing the troubleshooting period into several sub-periods, obtaining the maximum current value of the output circuit of the monitored object in the sub-period and marking it as the meter value of the sub-period, summing and averaging the meter values ​​of the monitored object in all sub-periods to obtain the discharge value of the monitored object, and performing variance calculation on the meter values ​​of the monitored object in all sub-periods to obtain the wave current value of the monitored object; The specific process of marking the cause of abnormal heating of the monitored object includes: obtaining the drainage threshold and the wave flow threshold through the storage module, and comparing the drainage value and the wave flow value with the drainage value and the wave flow value respectively: if the drainage value is less than or equal to the drainage threshold and the wave flow value is less than or equal to the wave flow threshold, it is determined that the cause of the abnormal heating is an abnormal external environment, and the abnormality investigation module sends an environmental adjustment signal to the mobile phone terminal of the manager; if the drainage value is less than or equal to the drainage threshold and the wave flow value is greater than the wave flow threshold, it is determined that the cause of the abnormal heating is poor contact of the wire, and the abnormality investigation module sends a contact abnormality signal to the mobile phone terminal of the manager; if the drainage value is greater than the drainage threshold and the wave flow value is less than or equal to the wave flow threshold, it is determined that the cause of the abnormal heating is a line short circuit, and the abnormality investigation module sends a short circuit signal to the controller and the mobile phone terminal of the manager, and the controller cuts off the output line of the monitored object after receiving the short circuit signal; if the drainage value is greater than the drainage threshold and the wave flow value is greater than the wave flow threshold, it is determined that the cause of the abnormal heating is a mismatch between the wire and the equipment, and the abnormality investigation module sends a matching abnormality signal to the mobile phone terminal of the manager; The process of obtaining the ambient humidity data HS includes: obtaining the air humidity value and humidity range of the external environment of the monitored object, marking the average value of the maximum value and the minimum value of the humidity range as the average humidity value, and marking the absolute value of the difference between the air humidity value and the average humidity value as the ambient humidity data HS; the process of obtaining the ambient temperature data HW includes: obtaining the air temperature value and temperature range of the external environment of the monitored object, marking the absolute value of the difference between the maximum value and the minimum value of the temperature range as the average temperature value, and marking the absolute value of the difference between the air temperature value and the average temperature value as the ambient temperature data HW; the altitude data HB is the altitude value of the monitored object; The specific process of predicting whether the monitored object has abnormal heating during the prediction period includes: obtaining an environmental interval matching the environmental coefficient HJ of the monitored object through the storage module and marking it as a marked interval, marking the heating data of the charging pile in the marked interval during the corresponding prediction period as marked data; establishing a rectangular coordinate system with the prediction period time as the X-axis and the heating coefficient FR of the monitored object during the prediction period as the Y-axis, marking a number of monitoring points in the rectangular coordinate system with the start time of the prediction period as the horizontal axis and the maximum value of the heating coefficient FR of the monitored object during the prediction period as the vertical axis, and connecting the monitoring points from left to right in sequence to obtain a monitoring polyline; and establishing a rectangular coordinate system with the marked data and the corresponding prediction period in the rectangular coordinate system. Mark several marked broken lines, mark the horizontal coordinate value of the monitoring point on the rightmost side of the monitoring broken line as Lo, make a ray perpendicular to the X-axis in the first quadrant of the rectangular coordinate system with the prediction point as the endpoint and mark it as the prediction ray, the coordinate of the prediction point is (Lo, 0), and multiple closed polygons are formed by the monitoring broken line, the marked broken line, the Y-axis and the prediction ray. The sum of the area values ​​of all closed polygons is marked as the fitting value of the marked broken line, and the marked broken line with the smallest fitting value is marked as the matching broken line. It is determined whether the charging pile corresponding to the matching broken line has abnormal heating within the corresponding prediction period: if so, a prediction warning signal is generated and sent to the mobile terminal of the manager; if not, no signal is generated.

2. According to the artificial intelligence-based charging environment temperature monitoring and alarm system of claim 1, it is characterized in that: After the prediction cycle is completed, the environmental coefficient HJ and the heating coefficient FR of the monitored object are sent to the storage module for storage. After receiving the environmental coefficient HJ of the monitored object, the storage module updates the environmental interval: the environmental range is composed of the maximum value of the environmental coefficient HJ and the environmental coefficient HJmin, and the environmental range is divided into several environmental intervals. The heating coefficient FR of the monitored object is matched with the corresponding environmental interval.